Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ATA
    -0.08
     ENTER
    -0.07
    。。。
    -0.07
     amy
    -0.07
    .linalg
    -0.07
     enforcement
    -0.07
    Counts
    -0.07
    _la
    -0.07
    .sender
    -0.07
     warranty
    -0.07
    POSITIVE LOGITS
    _altern
    0.08
     rabbits
    0.07
    쑈
    0.07
    投机
    0.07
    뵨
    0.07
    没人
    0.07
    滚滚
    0.07
    ﴫ
    0.07
    傀
    0.07
     After
    0.07
    Act Density 0.089%

    No Known Activations